# Sam Witteveen — 'RAON-1 Nano: Can a Tiny LLM Power Game NPCs?'

> Sam Witteveen tries KRAFTON's tiny Raon-1 nano model as the brain for game characters.

- Org: Sam Witteveen
- Date: 2026-11-17
- Category: video
- Source: https://www.youtube.com/watch?v=IRZqAdKcNTE
- Canonical page: https://ai-tldr.dev/releases/sam-witteveen-raon-1-nano-npcs-nov17/

## In short

Sam Witteveen tests KRAFTON's Raon-1 nano, a small Apache-2.0 model distilled from the larger Raon-1 mini, and asks whether a model this small can run the characters in a video game.

## What it is

'RAON-1 Nano: Can a Tiny LLM Power Game NPCs?' went up on Sam Witteveen's channel on 17 November 2026. The video looks at Raon-1 nano from KRAFTON, the games company, and why a games studio builds its own language models. It ends with a live demo and takeaways.

## How it works

According to KRAFTON's model card, Raon-1 nano is a dense Korean and English model with 1.5B effective parameters, made from the 30B-A4B Raon-1 mini preview mixture-of-experts model by pruning it into a dense model and then distilling it. The video walks through that MoE-to-dense step, the benchmarks, the parent model's free API and how to run the models locally.

## Why it matters

Game characters need a model that answers quickly on a player's own machine, not one that calls a large cloud model for every line. A 1.5B-parameter model with an Apache 2.0 license and builds for GGUF, MLX and LiteRT-LM is the kind of model a studio can ship inside a game.

## Who it's for

game developers and local-AI builders

## Try it

huggingface.co/KRAFTON/Raon-1-nano

## Links

- [Watch on YouTube](https://www.youtube.com/watch?v=IRZqAdKcNTE)
- [Raon-1 nano Model Card](https://huggingface.co/KRAFTON/Raon-1-nano)
- [Sam Witteveen](https://www.youtube.com/channel/UC55ODQSvARtgSyc8ThfiepQ)
